{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002515547480958703,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002795052756620781,
      "grad_norm": 5.359750747680664,
      "learning_rate": 2e-05,
      "loss": 18.5402,
      "step": 1
    },
    {
      "epoch": 0.0002795052756620781,
      "eval_loss": 4.651155471801758,
      "eval_runtime": 85.9405,
      "eval_samples_per_second": 17.535,
      "eval_steps_per_second": 8.774,
      "step": 1
    },
    {
      "epoch": 0.0005590105513241562,
      "grad_norm": 4.91422700881958,
      "learning_rate": 4e-05,
      "loss": 18.0204,
      "step": 2
    },
    {
      "epoch": 0.0008385158269862343,
      "grad_norm": 5.455460071563721,
      "learning_rate": 6e-05,
      "loss": 18.9182,
      "step": 3
    },
    {
      "epoch": 0.0008385158269862343,
      "eval_loss": 4.639312744140625,
      "eval_runtime": 85.7318,
      "eval_samples_per_second": 17.578,
      "eval_steps_per_second": 8.795,
      "step": 3
    },
    {
      "epoch": 0.0011180211026483125,
      "grad_norm": 5.132485389709473,
      "learning_rate": 8e-05,
      "loss": 17.421,
      "step": 4
    },
    {
      "epoch": 0.0013975263783103907,
      "grad_norm": 6.257484436035156,
      "learning_rate": 0.0001,
      "loss": 19.7695,
      "step": 5
    },
    {
      "epoch": 0.0016770316539724687,
      "grad_norm": 7.846843719482422,
      "learning_rate": 0.00012,
      "loss": 17.2393,
      "step": 6
    },
    {
      "epoch": 0.0016770316539724687,
      "eval_loss": 4.380094051361084,
      "eval_runtime": 86.1336,
      "eval_samples_per_second": 17.496,
      "eval_steps_per_second": 8.754,
      "step": 6
    },
    {
      "epoch": 0.001956536929634547,
      "grad_norm": 9.246593475341797,
      "learning_rate": 0.00014,
      "loss": 18.576,
      "step": 7
    },
    {
      "epoch": 0.002236042205296625,
      "grad_norm": 12.987396240234375,
      "learning_rate": 0.00016,
      "loss": 14.8416,
      "step": 8
    },
    {
      "epoch": 0.002515547480958703,
      "grad_norm": 14.694947242736816,
      "learning_rate": 0.00018,
      "loss": 13.1413,
      "step": 9
    },
    {
      "epoch": 0.002515547480958703,
      "eval_loss": 2.7212073802948,
      "eval_runtime": 86.3595,
      "eval_samples_per_second": 17.45,
      "eval_steps_per_second": 8.731,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3057630629068800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}